ReasoningSaturated
Trust Score:
25

ARC-AGI

Colored-grid abstraction tasks that test few-shot rule induction, not memorized facts, language fluency, or school math.

Launched: Refresh: static
Status Assessment (saturated):

ARC-AGI-1 remains useful as a historical abstraction benchmark, but the official ARC Prize leaderboard generated on 2026-07-23 lists multiple verified systems above 95% on the ARC-AGI-1 semi-private axis, including GPT-5.6 Sol at 97.5%. ARC Prize launched ARC-AGI-2 because ARC-AGI-1 had become too brute-forceable and less discriminative for frontier systems.

Performance Timeline

Longitudinal progression of model scores against human baselines.

Performance & Historical Trajectory

Empirical score progression across model release dates and evaluation rounds.

Independent Vendor-Reported Human Baseline (85.0%)
ModelScoreDateSource TypeProvenance
o3-preview-low (CoT + search/synthesis)75.7%2024-12-20vendor-reportedSource ↗
Jeremy Berman system53.6%2024-12-18independentSource ↗
o1-preview18%2024-09-13vendor-reportedSource ↗
GPT-4o5%2024-06-27vendor-reportedSource ↗
Claude 4.7 (High)93.5%2024-06-01vendor-reportedSource ↗
GPT-5.5 Pro (High)96.5%2024-06-01vendor-reportedSource ↗
GPT-5.6 Sol (xHigh)97.5%2024-06-01vendor-reportedSource ↗

Human Baseline & Difficulty Horizon

Calibrated human reference points, specialist benchmarks, and ceiling thresholds.
Measured Human Score85.0%Domain Expert Baseline
Baseline Protocol & Interpretation

Standard human solve rate on abstract visual reasoning grid transformation puzzles without training.

Metric & Scoring Methodology

Verification protocols, aggregation formulas, and specialized metric variants.
Primary Metric:task success rate on the evaluation split (%)
Scoring Engine:exact-match

Dataset & Compute Cost

Evaluation volume, public availability, API pricing, and local hardware requirements.
Total Dataset Size400Annotated evaluation items
Public Test SetPublicOpenly mirrored on repositories
Access GatingOpen AccessUnrestricted download
Evaluation LicenseOpen AccessDataset usage and redistribution terms
Frontier API Compute Cost:

$5 – $20 USD for full benchmark evaluation run on frontier APIs.

Recommended Local GPU Setup:

1x NVIDIA RTX 4090 (24GB) or A100 (40GB/80GB) via vLLM / SGLang

Official Dataset & Benchmark Files:Download / View Dataset Repository ↗

How to Run & Reproduce

Standardized evaluation protocols, CLI commands, and reproducible runner templates.
Prompt Regimezero-shot
Reasoning Modedirect
Sampling Temp0
Pass@k Budgetk = 1
Tools & SandboxPure Text
Scoring Verifierexact-match
Option AEleutherAI LM-Evaluation-Harness (Open-Weight Models)
lm_eval --model hf --model_args pretrained=<model_path> --tasks arc-agi --batch_size auto
Option BOpenCompass Evaluation Framework
opencompass --datasets arc-agi --models <model_config>
Python APIDeterministic Inference Loop Snippet
# Standard API Evaluation Loop
from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": prompt}],
    temperature=0.0,
)
Standardized Reporting Requirement:

When publishing results for ARC-AGI, always report the exact prompt template, few-shot exemplar ordering, sampling temperature (temperature=0), maximum reasoning budget tokens, and the precise timestamped model snapshot ID.

Contamination & Memorization Analysis

Audit of pretraining exposure risks, memorization vectors, and refresh policies.
Overall Contamination Risk:HIGH
Refresh Cadence:

Static fixed snapshot

Test Set Exposure:

Public on web / HuggingFace